Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    学院
    -0.06
     ως
    -0.06
    GHz
    -0.06
    .Never
    -0.06
     vše
    -0.06
     пись
    -0.06
     svo
    -0.06
     pare
    -0.06
     increasing
    -0.06
     Breath
    -0.06
    POSITIVE LOGITS
    érience
    0.07
    implement
    0.07
    uspendLayout
    0.06
    ırak
    0.06
    _GO
    0.06
    (meta
    0.06
    attachment
    0.06
    irl
    0.06
    "default
    0.06
    iyorum
    0.06
    Act Density 0.005%

    No Known Activations